Low Risk

search_code

search_code

How to control search_code ↓

AI agents call search_code to retrieve information from Carrot AI PM without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Based on the tool name 'search_code' and the context that this is a development tool in a spec-driven workflow, this appears to be a code search or discovery tool that retrieves code without modifying it.

From the tool's definition Tool name 'search_code' combined with context of a spec-driven development tool suggests code searching/retrieval functionality. No description provided, but the name strongly indicates a read-only query operation.

Documented attack patterns abuse exactly the kind of access search_code gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Carrot AI PM, and nothing reaches the server without passing your rules. This is the rule we recommend for search_code:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_code": {}
  }
}

search_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Carrot AI PM — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_code tool do? +

search_code. It is categorised as a Read tool in the Carrot AI PM MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_code? +

Register the Carrot AI PM MCP server in PolicyLayer and add a rule for search_code: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Carrot AI PM. Nothing to install.

What risk level is search_code? +

search_code is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_code? +

Yes. Add a rate_limit block to the search_code rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block search_code completely? +

Set action: deny in the PolicyLayer policy for search_code. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides search_code? +

search_code is provided by the Carrot AI PM MCP server (talvinder/carrot-ai-pm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Carrot AI PM tool call.

Deterministic rules across all 11 Carrot AI PM tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

11 Carrot AI PM tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.